import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("diffusers/consistency-models-test", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]These UNet2DModel checkpoints are small randomly-initialized U-Nets which accept 32x32 images for use in testing consistency models.
"test_unet_class_cond" is class-conditional (e.g. contains a class label embedding), while "test_unet" is not.
Please refer to the original model card for more information about consistency models.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support